CN111008340B - Course recommendation method, device and storage medium - Google Patents
Course recommendation method, device and storage medium Download PDFInfo
- Publication number
- CN111008340B CN111008340B CN201911320014.0A CN201911320014A CN111008340B CN 111008340 B CN111008340 B CN 111008340B CN 201911320014 A CN201911320014 A CN 201911320014A CN 111008340 B CN111008340 B CN 111008340B
- Authority
- CN
- China
- Prior art keywords
- course
- courses
- determining
- keywords
- index value
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 51
- 238000010606 normalization Methods 0.000 claims description 11
- 238000012163 sequencing technique Methods 0.000 claims description 2
- 238000004364 calculation method Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 6
- 101100517651 Caenorhabditis elegans num-1 gene Proteins 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 239000013598 vector Substances 0.000 description 2
- 239000000284 extract Substances 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9536—Search customisation based on social or collaborative filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/20—Education
- G06Q50/205—Education administration or guidance
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- Educational Administration (AREA)
- Educational Technology (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to a course recommendation method, an electronic device and a storage medium, wherein the method comprises the following steps: extracting course information from a database in the network learning system, wherein the course information comprises course identification, course names, course keywords and training classes to which the courses belong; calculating the similarity among the courses according to the course information, and taking the courses with the similarity larger than a first preset threshold value as similar courses to obtain a plurality of similar course sets; acquiring keywords of all courses in a plurality of similar course sets; determining a first keyword set of each similar course set according to keywords of all courses, wherein the first keyword set comprises at least one keyword with a frequency index value larger than a second preset threshold value; determining hot courses according to the first keyword set; and sending the course information of the hot course to a display terminal for displaying so as to prompt the user to be recommended to learn the hot course. The method and the device can enable the user to quickly receive the training of high-quality effective courses, and improve the learning quality and the learning efficiency.
Description
Technical Field
The embodiment of the invention relates to the technical field of internet, in particular to a course recommendation method, a course recommendation device and a storage medium.
Background
With the popularization and deep application of the internet, the network learning system becomes an important platform for people to learn knowledge, and the limitation of developing offline teaching training classes is overcome. Because the teaching course training quality is high, the student learning effect is good, many enterprises can develop different teaching course training aiming at different sub-companies or departments, and the student is trained by combining the teaching course and the network learning course.
Generally speaking, the class of the courses taught by the face-to-face training class can reflect the learning hotspots and demand points at the present stage to a certain extent, and the learning hotspots and demand points can provide effective references for course recommendation in the network learning system, so that the manager can upload the videos of the face-to-face courses to the network learning system for all students to learn.
However, the network course and the face-to-face course on the current network learning system are complicated, and a course recommendation system of the system is not formed, so that a student cannot learn a high-quality effective course more quickly, and the learning quality and efficiency are reduced.
Disclosure of Invention
Embodiments of the present invention provide a course recommendation method, a device and a storage medium, so as to solve the problems in the prior art that, due to the complicated network course and teaching process and the absence of a course recommendation system, a student cannot learn a high-quality effective course more quickly, and the learning quality and efficiency of the student are reduced.
A first aspect of an embodiment of the present invention provides a course recommendation method, including:
extracting course information from a database in the network learning system, wherein the course information comprises a course identification, a course name, a course keyword and a training class to which the course belongs;
calculating the similarity among the courses according to the course information, and taking the courses with the similarity larger than a first preset threshold value as similar courses to obtain a plurality of similar course sets;
acquiring keywords of all courses in the plurality of similar course sets;
determining a first keyword set of each similar course set according to keywords of all courses, wherein the first keyword set comprises at least one keyword of which the frequency index value is greater than a second preset threshold value;
determining hot courses according to the first keyword set;
and sending the course information of the hot course to a display terminal for displaying so as to prompt the user to be recommended to learn the hot course.
Optionally, the determining, according to the keywords of all the courses, the first keyword set of each similar course set includes:
determining a second keyword set of each similar course set according to keywords of all courses in each similar course set, wherein the second keyword set is a set formed by core keywords of which the corresponding course quantity is greater than a third preset threshold;
determining a course quantity index value, a training class quantity index value and a student quantity index value corresponding to each keyword in the second keyword set;
determining a frequency index value of each keyword according to the curriculum quantity index value, the training class quantity index value and the student quantity index value;
and determining a set consisting of keywords with the frequency index values larger than the second preset threshold value as a first keyword set of each similar course set.
Optionally, the determining, according to keywords of all courses in each similar course set, a second keyword set of each similar course set includes:
extracting core words in the keywords of all the courses in the similar course set, wherein the core words are words with the most intersection in the keywords;
taking keywords containing the core vocabulary as core keywords of the similar course set, and calculating the course number containing the core keywords in the similar course set;
and determining a set consisting of the core keywords of which the corresponding curriculum quantity is greater than the third preset threshold value as a second keyword set of the similar curriculum sets.
Optionally, the determining a course quantity index value, a training class quantity index value, and a trainee quantity index value corresponding to each keyword in the second keyword set includes:
calculating the sum of all the curriculum quantities in the similar curriculum sets containing the keywords, and determining the sum as a curriculum quantity index value corresponding to the keywords; and (c) and (d),
determining the course containing the keyword, and determining the number of training classes to which the course belongs as the index value of the number of training classes corresponding to the keyword; and the combination of (a) and (b),
and calculating the sum of the numbers of the students in the training class to which the course containing the keyword belongs, and determining the sum as the index value of the number of the students corresponding to the keyword.
Optionally, the determining a frequency index value of each keyword according to the curriculum quantity index value, the training class quantity index value and the trainee quantity index value includes:
respectively carrying out normalization processing on the curriculum quantity index value, the training class quantity index value and the student quantity index value;
and carrying out weighted summation on the normalized curriculum quantity index value, the normalized training class quantity index value and the normalized student quantity index value, and determining the sum value as the frequency index value of the keyword.
Optionally, the determining a popular course according to the first keyword set includes:
determining a characteristic similar course set, wherein the characteristic similar course set is a set formed by courses containing keywords in the first keyword set;
calculating the number of training classes to which each course belongs and the number of students of each course in the characteristic similar course set;
determining the heat index value of each course according to the number of training classes and the number of students to which each course belongs;
and determining hot courses in the characteristic similar course set according to the popularity index value of each course.
Optionally, the determining the heat index value of each course according to the number of training classes to which each course belongs and the number of students comprises:
respectively carrying out normalization processing on the number of training classes and the number of students to which each course belongs;
and carrying out weighted summation on the number of training classes to which each course belongs and the number of students after the normalization processing, and determining the sum as the heat index value of each course.
Optionally, the determining popular courses in the feature similar course set according to the popularity index value of each course includes:
sorting the courses in the characteristic similar course set according to the sequence of the popularity index values of all the courses from big to small;
and determining the previous preset number of courses as hot courses, or determining the courses with the hot index values larger than a fourth preset number threshold as the hot courses.
A second aspect of an embodiment of the present invention provides an electronic device, including: at least one processor and memory;
the memory stores computer execution instructions;
the at least one processor executing the computer-executable instructions stored in the memory causes the at least one processor to perform the course recommendation method of the first aspect of the embodiments of the present invention.
A third aspect of the embodiments of the present invention provides a computer-readable storage medium, in which computer-executable instructions are stored, and when a processor executes the computer-executable instructions, the course recommendation method according to the first aspect of the embodiments of the present invention is implemented.
According to the course recommendation method, the device and the storage medium provided by the embodiment of the invention, the course keywords are extracted from all the face-to-face courses and the network courses, the high-frequency keywords are extracted from all the keywords, the preset number of courses with the highest comprehensive indexes are selected from the courses containing the high-frequency keywords to serve as hot courses, and the hot courses are recommended to the student, so that the student can quickly learn high-quality courses, and the learning efficiency and the learning quality of the student are improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a diagram illustrating an application scenario of a course recommendation method according to an exemplary embodiment of the present invention;
FIG. 2 is a flowchart illustrating a course recommendation method in accordance with an exemplary embodiment of the present invention;
FIG. 3 is a flowchart illustrating a course recommendation method in accordance with another exemplary embodiment of the present invention;
FIG. 4 is a flowchart illustrating a course recommendation method in accordance with another exemplary embodiment of the present invention;
FIG. 5 is a block diagram of a course recommender as shown in an exemplary embodiment of the present invention;
fig. 6 is a schematic structural diagram of an electronic device according to an exemplary embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The terms "first," "second," "third," "fourth," and the like in the description and in the claims, as well as in the drawings, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are, for example, capable of operation in sequences other than those illustrated or otherwise described herein. Moreover, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
Currently, many enterprises will develop different face-to-face courses for different sub-companies or departments, and train students by combining the face-to-face courses with the online learning courses. Because the class of the teaching of the face-to-face training class can reflect the learning hotspots and demand points at the present stage to a certain extent, the learning hotspots and demand points can provide effective reference for course recommendation in the network learning system, and therefore, the manager can upload the video of the face-to-face course to the network learning system for all students to learn.
However, the network course and the face-to-face course on the network learning system are complicated, and a course recommendation system of the system is not formed, so that the student cannot learn the high-quality effective course more quickly, and the learning quality and efficiency are reduced.
In view of the above-mentioned drawbacks, the present invention provides a course recommendation method, apparatus, and storage medium, in which course keywords are extracted from all face-to-speak courses and network courses, high-frequency keywords are extracted from all the keywords, a preset number of courses with the highest comprehensive index are selected from the courses including the high-frequency keywords as hot courses, and the hot courses are recommended to a student or a trainee, so that the student can rapidly learn the high-quality courses, thereby improving the learning efficiency and learning quality of the student, and the trainee can train the student with reference to the hot courses, thereby improving the training efficiency and training quality.
Fig. 1 is an application scenario diagram illustrating a course recommendation method according to an exemplary embodiment of the present invention.
As shown in fig. 1, a server 102 extracts course information from a database 101 in a network learning system, where the course information includes a course identifier, a course name, a course keyword, and a training class to which the course belongs of at least one course; calculating the similarity between courses according to the course information, and taking the courses with the similarity larger than a first preset threshold value as similar courses to obtain a plurality of similar course sets; then acquiring keywords of all courses in the plurality of similar course sets; determining a first keyword set of each similar course set according to keywords of all courses, wherein the first keyword set comprises at least one keyword with a frequency index value larger than a second preset threshold value; determining hot courses according to the first keyword set; and finally, sending the course information of the hot course to a display terminal 103 for displaying so as to prompt the user to be recommended to learn the hot course.
Fig. 2 is a flowchart illustrating a course recommending method according to an exemplary embodiment of the present invention, where an execution subject of the method in this embodiment may be a server in the embodiment illustrated in fig. 1, or may be a terminal, such as a mobile terminal like a mobile phone, a tablet computer, and the like.
As shown in fig. 2, the method provided by this embodiment may include the following steps:
s201, extracting course information from a database in the network learning system, wherein the course information comprises a course identification, a course name, a course keyword and a training class to which the course belongs.
The courses in the database of the network learning system comprise a face-to-face course and a network recording course. The course identification and the course name are in one-to-one correspondence, and each course corresponds to a plurality of course keywords.
Since the work contents of different departments or different sub-companies of a company are different, training courses of training classes set up by each department or each sub-company are also different, and for parts with the same work contents of each department, the same course is used for training students in a plurality of training classes.
It should be noted that the training class information includes: keywords of all courses in the training class, and IDs (i.e., course identifications) of all courses, so that it can be determined to which subsidiary or department the course belongs through the course identifications.
S202, calculating the similarity between courses according to the course information, and taking the courses with the similarity larger than a first preset threshold value as similar courses to obtain a plurality of similar course sets.
The similarity is used for representing the similarity degree and the association degree between the courses, and the higher the similarity is, the higher the similarity degree or the association degree between the courses is.
Specifically, the method for calculating the similarity between courses may convert the keywords of each course into word vectors, and calculate the similarity between the word vectors, so as to obtain the similarity between the courses, and the specific calculation process may refer to a method for calculating the similarity in the prior art, which is not described in detail herein.
After the similarity between the courses is obtained, the courses with the similarity larger than a first preset threshold are taken as similar courses, and the similar courses are related to the coursesThe key words are put into the same set and defined as a similar course set, and the similar course set can be represented by A i It is shown that the process of the present invention,
indicating course ID, J i Represents a set A i The number of middle course IDs, I represents the number of similar course sets, thereby obtaining a plurality of similar course sets (such as A) 1 、A 2 、A 3 Etc.), each similar course set includes a plurality of similar courses (e.g., a) 1,1 、A 1,2 Etc.).
S203, obtaining the keywords of all the courses in the plurality of similar course sets.
Each course corresponds to at least one keyword, and each similar course set comprises at least one course.
Specifically, similar courses are collected as a i For example, a similar course set A is obtained i The keywords of each course are combined into a set and recorded as ACK i ，
Represents a set A i Each course keyword of, K i Indicating the number of keywords.
S204, determining a first keyword set of each similar course set according to keywords of all courses, wherein the first keyword set comprises at least one keyword of which the frequency index value is greater than a second preset threshold value.
Because each similar course set comprises a plurality of similar courses, and the plurality of courses in each similar course set have the same or similar keywords, a representative keyword can be selected from the keywords of the plurality of courses in each similar course set to serve as a core keyword of each similar course set, and then a high-frequency keyword of each similar course set is selected from the core keywords of each similar course set.
Specifically, referring to fig. 3, the method for determining the first keyword set of each similar course set may include the following steps:
s2041, determining a second keyword set of each similar course set according to keywords of all courses in each similar course set, wherein the second keyword set is a set formed by core keywords of which the corresponding course quantity is larger than a third preset threshold value.
Firstly, extracting core words in keywords of all courses in the similar course set, wherein the core words are words with the most intersection in the keywords;
in particular, from similar course set A i Set of keywords ACK i Determining the words with the most intersection as similar course set A i Core vocabulary of (W) i 。
For example, a set of keywords ACK i Is { cloud computing, cloud service, cloud technology, cloud application, big data }, then the most intersected words are "cloud", then W is i = { cloud }.
Then, taking the keywords containing the core vocabulary as the core keywords of the similar course set, and calculating the course number containing the core keywords in the similar course set;
specifically, all the core keywords constitute a core keyword set, which is denoted as TKW i For TKW i Each core keyword in the course set A is calculated i Including the number of courses for the core keyword.
For example, if the core vocabulary is "cloud", the core keywords are "cloud computing", "cloud service", "cloud technology", and "cloud application". Then calculate similar course set A i In the method, the keywords of which courses comprise 'cloud computing', the keywords of which courses comprise 'cloud service', and the like, so that the number of courses corresponding to each core keyword is obtainedAmount (v).
And finally, determining a set formed by the core keywords of which the corresponding curriculum quantity is greater than the third preset threshold value as a second keyword set of the similar curriculum set.
The third preset threshold value can be set according to actual requirements.
For example, the third preset threshold is 8. The number of courses including "cloud computing" is 10, the number of courses including "cloud service" is 9, the number of courses including "cloud technology" is 5, and the number of courses including "cloud application" is 11, so that the set composed of the core keywords "cloud computing", "cloud service", and "cloud application" is the similar course set a i The second set of keywords.
Or, the core keywords are sequenced according to the sequence of the number of courses from small to large, and N keywords with the highest number of courses are selected as a similar course set A i Second set of keywords, which may be denoted as K i ，K i ＝{K i,n ,n＝1,2,3,…N i The union of the second keyword sets of all similar course sets is denoted as TK,
for example, N is 3, and similar courses A are set according to the sequence of the number of courses from top to bottom i The first is 'cloud application', the second is 'cloud computing', the third is 'cloud service', and the fourth is 'cloud technology', then the first 3 keywords are selected to obtain a similar course set A i Second set of keywords K i Is { cloud application, cloud computing, cloud service }.
S2042, determining a course quantity index value, a training class quantity index value and a student quantity index value corresponding to each keyword in the second keyword set.
In some embodiments, the method for calculating the class number index value, the training class number index value and the student number index value corresponding to each keyword in the second keyword set includes:
calculating the sum of all course quantities in the similar course set containing the keywords, and determining the sum as a course quantity index value corresponding to the keywords;
specifically, the index value of the number of courses is recorded as P1 k If the key word TK k Only appearing in only one set A of similar courses i Second set of keywords K i Middle and similar course set A i The number of courses contained in is J i Then let P1 k ＝J i . If the key word TK k Now a second set of keywords K of two or more similar course sets i In the middle, then order
Wherein
For example, the keyword TK k Is a "cloud application" which appears both in a similar course set A 1 Second set of keywords K 1 Middle (i.e. TK) k ∈K 1 ) Also appear in the similar course set A 2 Second set of keywords K 2 Middle (i.e. TK) k ∈K 2 ) And, similar course set A 1 Including 50 courses, similar course set A 2 The number of courses is 40, then the index value P1 of the number of courses of the keyword' cloud application k Is 90.
Determining the course containing the keyword, and determining the number of training classes to which the course belongs as the index value of the number of training classes corresponding to the keyword;
specifically, the index value of the number of training classes is recorded as P2 k Acquiring a keyword set of courses set by the training class from a database of the network learning system, and recording the keyword set as CKword p P =1,2,3, \ 8230, P, P being the number of training classes, then,
wherein
And calculating the sum of the numbers of the students in the training class to which the curriculum containing the keyword belongs, and determining the sum as the index value of the number of the students corresponding to the keyword.
Specifically, the student number index value is represented as P3 k Acquiring the number of trainees corresponding to each training class from the database of the network learning system and recording the number as CNum p P =1,2,3, \ 8230, P, P being the number of training classes, then,
wherein
S2043, determining the frequency index value of each keyword according to the course number index value, the training class number index value and the student number index value.
Specifically, the frequency index value of each keyword consists of three index values P1 k ，P2 k And P3 k And (4) comprehensively calculating.
Optionally, respectively performing normalization processing on the curriculum quantity index value, the training class quantity index value and the student quantity index value;
for the index P1 k Taking the largest M values (e.g. M = 20), i.e. let P1 0 ＝max(P1 k ,k＝1,2,3,…,M)，P1 0 Not equal to 0. Then, normalization processing is carried out, and the index value of the number of courses after normalization processing is recorded as NP1 k Let NP1 k ＝P1 k /P1 0 ，k＝1,2,3,…,M)。
The same calculation method is adopted to obtain the index value of the training class number after the normalization processing and record the index value as NP2 k And student figure index value NP3 k 。
And carrying out weighted summation on the normalized curriculum quantity index value, the normalized training class quantity index value and the normalized student quantity index value, and determining the sum value as the frequency index value of the keyword.
Wherein, the calculation formula of the weighted summation is TP k ＝α×NP1 k +β×NP2 k +γ×NP3 k Wherein, α, β, γ ∈ [0,1 ]]And α + β + γ =1. Wherein, TP k The frequency index values of the keywords are represented, and alpha, beta and gamma are all weight coefficients.
S2044, determining a set consisting of the keywords with the frequency index values larger than the second preset threshold value as a first keyword set of each similar course set.
The second preset threshold value can be set according to actual requirements.
For example, similar course set A i Second set of keywords K i And { cloud application, cloud computing, cloud service }, where the respective frequency index values of the cloud application, the cloud computing, the cloud service, and the cloud service are 20, 25, 15, and 30, respectively, and the second preset threshold is 19, then. Determining a set consisting of keyword cloud application with a frequency index value larger than 19, cloud computing and cloud service as a similar course set A i The first set of keywords.
Or, according to TP k Sequencing the elements in the TK set from large to small, taking the M2 elements with higher values as high-frequency keywords, taking the set consisting of the high-frequency keywords as a first keyword set, and recording as TKW, wherein TKW = { TKW = m M =1,2,3, \8230; M2}, where the value of M2 may be set as desired, or may be a default value, such as M2=10.
S205, determining a hot course according to the first keyword set.
Specifically, referring to fig. 4, the method for determining a popular course according to the first keyword set may include the following steps:
s2051, determining a characteristic similar course set, wherein the characteristic similar course set is a set formed by courses containing keywords in the first keyword set.
Obtaining similar course sets containing high-frequency keywords from all similar course sets, forming characteristic similar course sets, and recording as PA, PA = { A = q Q =1,2,3, \ 8230; }. The high-frequency keywords are keywords in the first keyword set.
For example, similar course set A 1 、A 2 And A 3 Containing high frequency keywords, then the feature-similar course set PA = { a 1 ,A 2 ,A 3 }。
And S2052, calculating the number of training classes to which each course belongs and the number of students of each course in the characteristic similar course set.
In particular, for similar course set A q Calculating each course in the set (denoted as A) q,j ) The number of training classes is recorded as F1 q,j . In the database of the network learning system, the course A is obtained according to the course ID q,j The number of the training classes is recorded as Num1 q,j Let F1 be q,j ＝Num1 q,j 。
For similar course set A q Calculating each course in the set (denoted as A) q,j ) The number of students in (1), denoted as F2 q,j . In the database of the network learning system, the course A is obtained according to the course ID q,j The numbers of the trainees in the training class are summed and recorded as Num2 q,j Let F2 be q,j ＝Num2 q,j 。
For example, course A q,j Belonging to a first training class and a second training class, wherein the number of students in the first training class is 101, the number of students in the second training class is 90, and then course A q,j The number of trainees is 191.
S2053, determining the heat index value of each course according to the number of training classes and the number of students to which each course belongs;
for similar course set A q Computing each course A in the set q,j The heat index value of (D) is denoted as TF q,j Let TF q,j ＝f(Num1 q,j ,Num2 q,j ) Wherein f is a calculation function, the calculation method thereofThe method is that the number of training classes and the number of students belonging to each course are respectively normalized; and carrying out weighted summation on the number of training classes to which each course belongs and the number of students after the normalization processing, and determining the sum value as the heat index value of each course.
And S2054, determining hot courses in the characteristic similar course set according to the hot index value of each course.
Specifically, the courses in the characteristic similar course set are sequenced according to the sequence of the heat index value of each course from large to small;
determining the previous courses with the preset number as hot courses, or determining the courses with the heat index values larger than a fourth preset number threshold value as the hot courses.
For example, if the preset number is 3, the similar course set A is selected q Taking three courses with the highest degree of heat index value ranking 3 as hot courses; or, if the fourth preset number threshold is 50, the lesson with the popularity index value larger than 50 is taken as the popular lesson.
And S206, sending the course information of the hot course to a display terminal for displaying so as to prompt the user to be recommended to learn the hot course.
In this embodiment, the course keywords are extracted from all the professors and network courses, the core keywords are selected from all the keywords, the high-frequency keywords are extracted from the core keywords, then the preset number of courses with the highest comprehensive indexes are selected from the courses containing the high-frequency keywords to serve as hot courses, and the hot courses are recommended to the trainees or training staff, so that the trainees can rapidly learn the high-quality courses, the learning efficiency and the learning quality of the trainees are improved, and the trainees can train the trainees by referring to the hot courses, and the training efficiency and the training quality are improved.
Fig. 5 is a schematic structural diagram of a course recommending apparatus according to an exemplary embodiment of the present invention.
As shown in fig. 5, the course recommending apparatus provided in the present embodiment includes:
the information extraction module 501 is configured to extract course information from a database in the network learning system, where the course information includes a course identifier, a course name, a course keyword, and a training class to which the course belongs.
The similarity calculation module 502 is configured to calculate similarity between courses according to the course information, and obtain a plurality of similar course sets by using courses with similarity greater than a first preset threshold as similar courses.
A keyword obtaining module 503, configured to obtain keywords of all the courses in the plurality of similar course sets.
A keyword determining module 504, configured to determine, according to keywords of all courses, a first keyword set of each similar course set, where the first keyword set includes at least one keyword whose frequency index value is greater than a second preset threshold value.
And a course determining module 505, configured to determine a hot course according to the first keyword set.
And the course recommending module 506 is configured to send the course information of the hot course to a display terminal for displaying, so as to prompt the user to be recommended to learn the hot course.
For detailed functional description of each module in this embodiment, reference is made to the description of the embodiment of the method, and the detailed description is not provided herein.
Fig. 6 is a schematic diagram of an electronic hardware structure according to an embodiment of the present invention. As shown in fig. 6, the electronic device 600 provided in the present embodiment includes: at least one processor 601 and memory 602. The processor 601 and the memory 602 are connected by a bus 603.
In this embodiment, the electronic device may be a server, or may also be a terminal, such as a mobile phone, a tablet computer, and the like.
In a specific implementation, the at least one processor 601 executes the computer-executable instructions stored in the memory 602 to cause the at least one processor 601 to perform the course recommendation method in the above method embodiments.
For the specific implementation process of the processor 601, reference may be made to the above method embodiments, which implement principles and technical effects similar to each other, and details are not described herein again.
In the embodiment shown in fig. 6, it should be understood that the Processor may be a Central Processing Unit (CPU), other general purpose processors, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of a method disclosed in connection with the present invention may be embodied directly in a hardware processor, or in a combination of hardware and software modules.
The memory may comprise high speed RAM memory and may also include non-volatile storage NVM, such as at least one disk memory.
The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, an Extended ISA (EISA) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, the buses in the figures of the present application are not limited to only one bus or one type of bus.
Another embodiment of the present application provides a computer-readable storage medium, in which computer-executable instructions are stored, and when a processor executes the computer-executable instructions, the course recommendation method in the above method embodiment is implemented.
The computer-readable storage medium may be implemented by any type of volatile or non-volatile storage device or combination thereof, such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disk. Readable storage media can be any available media that can be accessed by a general purpose or special purpose computer.
An exemplary readable storage medium is coupled to the processor such the processor can read information from, and write information to, the readable storage medium. Of course, the readable storage medium may also be an integral part of the processor. The processor and the readable storage medium may reside in an Application Specific Integrated Circuits (ASIC). Of course, the processor and the readable storage medium may also reside as discrete components in the apparatus.
Those of ordinary skill in the art will understand that: all or a portion of the steps of implementing the above-described method embodiments may be performed by hardware associated with program instructions. The program may be stored in a computer-readable storage medium. When executed, the program performs steps comprising the method embodiments described above; and the aforementioned storage medium includes: various media that can store program codes, such as ROM, RAM, magnetic or optical disks.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.
Claims (7)
1. A course recommendation method, comprising:
extracting course information from a database in the network learning system, wherein the course information comprises a course identification, a course name, a course keyword and a training class to which the course belongs;
calculating the similarity between courses according to the course information, and taking the courses with the similarity larger than a first preset threshold value as similar courses to obtain a plurality of similar course sets;
acquiring keywords of all courses in the plurality of similar course sets;
determining a first keyword set of each similar course set according to keywords of all courses, wherein the first keyword set comprises at least one keyword of which the frequency index value is greater than a second preset threshold value;
determining hot courses according to the first keyword set;
sending the course information of the hot courses to a display terminal for displaying so as to prompt a user to be recommended to learn the hot courses;
determining a first keyword set of each similar course set according to keywords of all courses, including:
determining a second keyword set of each similar course set according to keywords of all courses in each similar course set, wherein the second keyword set is a set formed by core keywords of which the corresponding course quantity is greater than a third preset threshold;
determining a course number index value, a training class number index value and a student number index value corresponding to each keyword in the second keyword set;
respectively carrying out normalization processing on the curriculum quantity index value, the training class quantity index value and the student quantity index value;
carrying out weighted summation on the normalized curriculum quantity index value, the normalized training class quantity index value and the normalized student quantity index value, and determining the sum value as the frequency index value of the keyword;
determining a set formed by keywords with frequency index values larger than the second preset threshold value as a first keyword set of each similar course set;
determining a hot course according to the first keyword set, including:
determining a characteristic similar course set, wherein the characteristic similar course set is a set formed by courses containing keywords in the first keyword set;
calculating the number of training classes to which each course belongs and the number of students of each course in the characteristic similar course set;
determining the heat index value of each course according to the number of training classes and the number of students to which each course belongs;
and determining hot courses in the characteristic similar course set according to the popularity index value of each course.
2. The method as claimed in claim 1, wherein the determining the second keyword set of each similar course set according to keywords of all courses in each similar course set comprises:
extracting core words in keywords of all courses in the similar course set, wherein the core words are words with the most intersection in the keywords;
taking keywords containing the core vocabulary as core keywords of the similar course set, and calculating the course number containing the core keywords in the similar course set;
and determining a set consisting of the core keywords of which the corresponding curriculum number is greater than the third preset threshold value as a second keyword set of the similar curriculum set.
3. The method of claim 1, wherein determining a class number index value, a training class number index value, and a trainee number index value for each keyword in the second set of keywords comprises:
calculating the sum of all course quantities in the similar course set containing the keywords, and determining the sum as a course quantity index value corresponding to the keywords; and (c) and (d),
determining the course containing the keyword, and determining the number of training classes to which the course belongs as the index value of the number of training classes corresponding to the keyword; and (c) and (d),
and calculating the sum of the numbers of the students in the training class to which the course containing the keyword belongs, and determining the sum as the index value of the number of the students corresponding to the keyword.
4. The method of claim 1, wherein determining the heat index value for each class based on the number of training classes and the number of trainees to which each class belongs comprises:
respectively carrying out normalization processing on the number of training classes and the number of students to which each course belongs;
and carrying out weighted summation on the number of training classes to which each course belongs and the number of students after the normalization processing, and determining the sum as the heat index value of each course.
5. The method as claimed in claim 1, wherein the determining hot courses in the feature-similar course set according to the popularity index value of each course comprises:
sequencing the courses in the characteristic similar course set according to the sequence of the popularity index value of each course from large to small;
and determining the previous preset number of courses as hot courses, or determining the courses with the hot index values larger than a fourth preset number threshold as the hot courses.
6. An electronic device, comprising: at least one processor and a memory;
the memory stores computer execution instructions;
execution of the computer-executable instructions stored by the memory by the at least one processor causes the at least one processor to perform the course recommendation method of any one of claims 1-5.
7. A computer-readable storage medium, having stored thereon computer-executable instructions, which when executed by a processor, implement the course recommendation method of any one of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911320014.0A CN111008340B (en) | 2019-12-19 | 2019-12-19 | Course recommendation method, device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911320014.0A CN111008340B (en) | 2019-12-19 | 2019-12-19 | Course recommendation method, device and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111008340A CN111008340A (en) | 2020-04-14 |
| CN111008340B true CN111008340B (en) | 2022-11-29 |
Family
ID=70117660
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911320014.0A Active CN111008340B (en) | 2019-12-19 | 2019-12-19 | Course recommendation method, device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111008340B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113656705B (en) * | 2021-08-31 | 2024-02-20 | 中国平安财产保险股份有限公司 | Course recommendation method, device, equipment and storage medium based on artificial intelligence |
| CN113837322B (en) * | 2021-11-04 | 2023-05-30 | 中国联合网络通信集团有限公司 | Course classification processing method, device, equipment and medium |
| CN117009829A (en) * | 2023-10-07 | 2023-11-07 | 成都华栖云科技有限公司 | Similarity recognition method and device for recorded and broadcast courses |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103955470B (en) * | 2014-03-28 | 2017-05-10 | 华为技术有限公司 | hotspot topic pushing method and device |
| CN105069102B (en) * | 2015-08-03 | 2017-05-24 | 百度在线网络技术（北京）有限公司 | Information push method and apparatus |
| CN105528432B (en) * | 2015-12-15 | 2019-04-26 | 北大方正集团有限公司 | A kind of digital resource hot spot generation method and device |
| CN106023015B (en) * | 2016-05-18 | 2020-10-09 | 腾讯科技（深圳）有限公司 | Course learning path recommendation method and device |
| CN109299372B (en) * | 2018-10-18 | 2021-03-16 | 浙江正元智慧科技股份有限公司 | Intelligent course selection recommendation method based on collaborative filtering |
| CN109766492B (en) * | 2018-12-24 | 2020-10-30 | 中国联合网络通信集团有限公司 | Learning recommendation method, device, equipment and readable medium |
-
2019
- 2019-12-19 CN CN201911320014.0A patent/CN111008340B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN111008340A (en) | 2020-04-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111008340B (en) | Course recommendation method, device and storage medium | |
| US20220391773A1 (en) | Method and system for artificial intelligence learning using messaging service and method and system for relaying answer using artificial intelligence | |
| CN112346567B (en) | Virtual interaction model generation method and device based on AI (Artificial Intelligence) and computer equipment | |
| CN110737859B (en) | UP master matching method and device | |
| CN109816265B (en) | Knowledge characteristic mastery degree evaluation method, question recommendation method and electronic equipment | |
| US20140030681A1 (en) | Activity-oriented Studying Method in an Online-to-offline Manner | |
| US20210248687A1 (en) | System and method for predicting engagement on social media | |
| CN110737774A (en) | Book knowledge graph construction method, book recommendation method, device, equipment and medium | |
| CN116204714A (en) | Recommendation method, recommendation device, electronic equipment and storage medium | |
| CN111813993A (en) | Video content expanding method and device, terminal equipment and storage medium | |
| CN109087224A (en) | A method of the individual demand based on examinee carries out college entrance will recommendation and prediction | |
| CN116541711A (en) | Model training method, course recommendation method, device, equipment and medium | |
| CN111259251A (en) | Method and device for recommending annotation task | |
| CN110765278A (en) | Method for searching similar exercises, computer equipment and storage medium | |
| US20170193620A1 (en) | Associate a learner and learning content | |
| CN112434144A (en) | Method, device, electronic equipment and computer readable medium for generating target problem | |
| CN114067343A (en) | Data set construction method, model training method and corresponding device | |
| CN114297372A (en) | Personalized note generation method and system | |
| CN112380263A (en) | Teaching data recommendation method and device | |
| Furtado et al. | The effect on new knowledge and reviewed knowledge caused by the positioning task in closed concept maps | |
| US20190304040A1 (en) | System and Method for Vetting Potential Jurors | |
| CN114237460B (en) | Label display method, device, terminal, storage medium and computer program product | |
| CN111723164A (en) | Address information processing method and device | |
| CN111126823B (en) | Information processing method, apparatus and storage medium | |
| CN109636693A (en) | A kind of exercise purpose recommended method and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |